INDEX

Explanations

actions, promotion, establishment

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

HashCode

-0.27

cken

-0.27

ensa

-0.25

 humming

-0.24

èªĵ

-0.24

ale

-0.24

coc

-0.24

omes

-0.24

cov

-0.24

pov

-0.24

POSITIVE LOGITS

uable

0.32

atch

0.28

/edit

0.27

 assignable

0.27

Unable

0.27

å¾Ĺå¤©çĭ¬åİļ

0.26

 Unlimited

0.26

/></

0.26

èĥ½å¤Ł

0.26

uggle

0.25

Activations Density 0.393%

actions, promotion, establishment

No Comments

No Known Activations