INDEX

Explanations

Incomplete word prefixes

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

alk

-0.29

ritz

-0.29

iq

-0.26

 desk

-0.26

zek

-0.25

ç¦ģåĮº

-0.25

 recommand

-0.25

èĤĿèĦı

-0.25

ç¥ŀç»ıç³»ç»Ł

-0.25

ÙĥÙĨ

-0.25

POSITIVE LOGITS

 freely

0.27

 onSuccess

0.27

åŁºæķ°

0.26

æ¨ª

0.26

umbled

0.26

Salt

0.26

orelease

0.25

 Salt

0.25

éĨ¯

0.25

äºĴåĬ©

0.25

Activations Density 0.014%

Incomplete word prefixes

No Comments

No Known Activations