INDEX

Explanations

created

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

atics

-0.31

gÄ±

-0.27

<_

-0.27

sg

-0.26

 sÄ±

-0.26

mog

-0.25

.snapshot

-0.25

WG

-0.25

<tag

-0.25

é¸ł

-0.24

POSITIVE LOGITS

ankind

0.28

äººä»¬å¯¹

0.24

Addon

0.24

DownList

0.24

å¹´çĶ±

0.24

ased

0.23

stinence

0.23

ressed

0.23

rej

0.23

jual

0.23

Activations Density 0.004%

created

No Comments

No Known Activations