INDEX

Explanations

Two-letter abbreviations

np_max-act · gemini-2.0-flash

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

abouts

-0.28

ÑĩÑĮ

-0.26

 Fram

-0.26

 Ranking

-0.25

avs

-0.24

 infinity

-0.24

 instrument

-0.24

 stagger

-0.24

 Territories

-0.23

guide

-0.23

POSITIVE LOGITS

erg

0.26

skin

0.25

aded

0.24

igen

0.24

anim

0.24

æĥĿ

0.24

erc

0.24

ocracy

0.23

è¯±

0.22

osphere

0.22

Activations Density 0.215%

Two-letter abbreviations

No Comments

No Known Activations