INDEX

Explanations

se

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 Nearby

-0.27

amarin

-0.26

åĵįåºĶ

-0.26

onders

-0.25

 Parkway

-0.25

altÄ±

-0.25

æŁ¥çľĭæĽ´å¤ļ

-0.25

 vite

-0.25

äºĶä¸Ģ

-0.24

 ComVisible

-0.24

POSITIVE LOGITS

ema

0.28

ç»¼

0.28

esa

0.28

çŁĽ

0.26

ort

0.25

OLA

0.25

wid

0.25

[#

0.25

è²Į

0.25

iez

0.24

Activations Density 0.802%

se

No Comments

No Known Activations