INDEX

Explanations

Sentence beginnings, stop words

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_10.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.10.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-pol

-0.28

 exporters

-0.27

åĮ»æ²»

-0.27

æ°´éĩı

-0.27

æĹ¦

-0.26

ozo

-0.25

 Sellers

-0.25

 Actors

-0.24

 tame

-0.24

ctxt

-0.23

POSITIVE LOGITS

 autofocus

0.28

 openid

0.26

 yielded

0.26

è¿ĺæľīä»Ģä¹Ī

0.25

itory

0.25

ç»

0.24

 miniature

0.24

orton

0.24

ogn

0.24

avia

0.23

Activations Density 0.003%

Sentence beginnings, stop words

No Comments

No Known Activations