INDEX

Explanations

naming, named after

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

hq

-0.31

çķĭ

-0.26

ãĤĴæĦŁãģĺ

-0.26

æ³¨å®ļ

-0.25

dq

-0.25

mj

-0.24

æĦŁãģĺãĤĭ

-0.24

æĥħåķĨ

-0.24

åŃĲå¼¹

-0.24

hlen

-0.24

POSITIVE LOGITS

 ç¬

0.33

 gimm

0.25

pen

0.25

ä¹³

0.25

 invention

0.25

å¼Ģåıĳå»ºè®¾

0.25

 African

0.25

pen

0.25

Mag

0.25

oor

0.24

Activations Density 0.007%

naming, named after

No Comments

No Known Activations