INDEX

Explanations

natural

np_max-act · gemini-2.0-flash

phrases that describe something as occurring in or derived from nature, typically using an adjective before a noun in scientific or technical contexts.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸İåħ¶

-0.27

itm

-0.27

 worth

-0.27

åħ¸åŀĭ

-0.27

oxide

-0.27

arts

-0.26

æģ¶åĬ£

-0.26

æŀģé«ĺ

-0.25

 hiáº¿m

-0.24

visual

-0.24

POSITIVE LOGITS

ziel

0.28

izzer

0.26

erg

0.25

itori

0.24

å¢ħ

0.24

ulatory

0.23

zig

0.23

 bodily

0.23

izza

0.23

SSF

0.23

Activations Density 0.028%

natural

phrases that describe something as occurring in or derived from nature, typically using an adjective before a noun in scientific or technical contexts.

No Comments

No Known Activations