INDEX

Explanations

"Ab", "el", or "Bellev"

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

çŃ¹èµĦ

-0.31

esus

-0.28

ansa

-0.27

culus

-0.25

ç°¿

-0.24

 timed

-0.24

ales

-0.24

é«ĺçº§

-0.24

 karÅŁ

-0.24

ÑĩÐ¸ÑģÐ»ÐµÐ½

-0.24

POSITIVE LOGITS

 Drag

0.27

 cord

0.26

_norm

0.25

Ã§a

0.25

 Dragons

0.25

TEE

0.25

åľŃ

0.25

å°¾å·´

0.24

stra

0.24

 Trom

0.24

Activations Density 0.029%

"Ab", "el", or "Bellev"

No Comments

No Known Activations