INDEX

Explanations

formal writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä»Ĺ

-0.29

icast

-0.26

buff

-0.25

åĵĢ

-0.24

å¸Į

-0.24

æ´½

-0.24

ÑĢÐ°Ñī

-0.24

Append

-0.24

radi

-0.24

åĪĩ

-0.24

POSITIVE LOGITS

 Contr

0.25

çļĦåŃĺåľ¨

0.25

xBC

0.24

åħĭæĸ¯

0.24

__/

0.24

lify

0.24

ansa

0.24

Contr

0.23

"]"

0.23

è®¡éĩı

0.23

Activations Density 0.130%

formal writing

No Comments

No Known Activations