INDEX

Explanations

descriptive adjectives

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dennis

-0.26

 giá»ĳng

-0.24

["+

-0.24

;break

-0.24

 till

-0.23

,,,

-0.23

bt

-0.23

[['

-0.23

Ta

-0.23

(()

-0.23

POSITIVE LOGITS

åĭĥ

0.29

emain

0.28

rong

0.26

agara

0.25

aning

0.25

Cls

0.25

stim

0.25

ç«Ļ

0.25

nehmer

0.25

æ³¨

0.24

Activations Density 0.007%

descriptive adjectives

No Comments

No Known Activations