INDEX

Explanations

specializes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑģÑĤÐ°Ð²ÐºÐ°

-0.27

ionale

-0.25

erb

-0.25

è²«

-0.25

éĹ®ä¸ĸ

-0.24

Å¼e

-0.24

å¥½å¤Ħ

-0.24

ignment

-0.24

agger

-0.24

emales

-0.24

POSITIVE LOGITS

ndon

0.31

æĭİ

0.30

 developing

0.28

-mf

0.27

ä»İäºĭ

0.26

 Charlotte

0.26

 develop

0.26

ä¸ĢåĲį

0.25

ez

0.25

anas

0.25

Activations Density 0.036%

specializes

No Comments

No Known Activations