INDEX

Explanations

Punctuation/code symbols

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

iÃ«

-0.28

åŁł

-0.27

iete

-0.26

iet

-0.25

Ĥæķ°

-0.24

Rew

-0.24

 Analysis

-0.24

ieten

-0.24

isure

-0.24

tics

-0.23

POSITIVE LOGITS

çľĭæĿ¥

0.29

æŁłæª¬

0.29

æķ´è½¦

0.27

£

0.26

arse

0.24

 chained

0.24

 whole

0.23

though

0.23

ç§ĭåĨ¬

0.23

çĶ²éĨĽ

0.23

Activations Density 0.129%

Punctuation/code symbols

No Comments

No Known Activations