INDEX

Explanations

possessive

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿ĺä¸įå¤Ł

-0.30

ewe

-0.26

htt

-0.25

<p

-0.24

èĻļæŀĦ

-0.24

å¼Ģçİ©ç¬ĳ

-0.24

å¾Ĺä¸įåĪ°

-0.24

âĵĺ

-0.24

.AddParameter

-0.24

 Valent

-0.24

POSITIVE LOGITS

 strr

0.27

atorium

0.25

#%

0.24

weise

0.24

hlen

0.24

åĲĪä½ľåħ³ç³»

0.24

unu

0.24

 echoing

0.24

è°´

0.24

quo

0.24

Activations Density 0.005%

possessive

No Comments

No Known Activations