INDEX

Explanations

sid

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

 query

-0.28

.query

-0.27

query

-0.26

æŁ¥è¯¢

-0.26

 HRESULT

-0.25

ENE

-0.25

èĹķ

-0.25

EG

-0.24

æģĥ

-0.24

POSITIVE LOGITS

æ¼Ĥäº®

0.27

å¹³æĿ¿

0.27

çħħ

0.27

 nicely

0.26

áºı

0.26

 Conspiracy

0.25

kest

0.24

ãĤĩãģĨ

0.24

resco

0.24

å¾ģéĽĨ

0.24

Activations Density 0.086%

sid

No Comments

No Known Activations