INDEX

Explanations

answer

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

éĤ£æ®µ

-0.31

Knife

-0.30

burgh

-0.28

rÃ´

-0.28

ummy

-0.26

Ãªs

-0.26

tant

-0.25

(XML

-0.25

MYSQL

-0.24

oric

-0.24

POSITIVE LOGITS

hit

0.29

ÄĻp

0.28

idon

0.27

hit

0.27

oplevel

0.27

å¹¸è¿Ĳ

0.26

akra

0.26

previous

0.26

 layer

0.26

ord

0.24

Activations Density 0.005%

answer

No Comments

No Known Activations