INDEX

Explanations

kinds types

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

çģ¶

-0.34

Mixin

-0.27

_self

-0.27

rem

-0.26

cent

-0.26

care

-0.26

ublic

-0.25

ÙĪØ±Ø©

-0.25

rem

-0.24

numer

-0.24

POSITIVE LOGITS

éĢ»

0.31

longleftrightarrow

0.27

å¼Ģçİ©ç¬ĳ

0.27

éĢ»è¾ĳ

0.26

 Holdings

0.25

(':')[

0.25

SearchTree

0.25

 longtime

0.25

æłĬ

0.24

æĢĢæĬ±

0.24

Activations Density 0.836%

kinds types

No Comments

No Known Activations