INDEX

Explanations

er

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Neil

-0.28

UEL

-0.25

JNI

-0.25

ITA

-0.25

eling

-0.25

ITU

-0.25

ä»ĵ

-0.24

err

-0.24

.stringify

-0.24

uit

-0.24

POSITIVE LOGITS

çī¹åĪ«å£°æĺİ

0.27

 Radical

0.26

[arr

0.25

ç¿®

0.25

 washington

0.25

trx

0.25

.setColor

0.24

æ¯Ķè¾ĥç®Ģåįķ

0.24

 Roose

0.24

ç®ª

0.24

Activations Density 0.196%

er

No Comments

No Known Activations