INDEX

Explanations

statement

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

èµ°åİ»

-0.26

 obstruct

-0.26

 walk

-0.26

 Ð¾Ð±ÑīÐµÑģÑĤÐ²

-0.25

ANTS

-0.25

 robbed

-0.25

 watch

-0.24

rar

-0.24

ugh

-0.24

 respect

-0.24

POSITIVE LOGITS

åĬĽè¿ĺæĺ¯

0.28

 Comes

0.26

ensem

0.26

 Come

0.25

"+↵

0.25

æºĲèĩª

0.25

 ÑĢÐµÐ¹

0.24

Come

0.24

 repl

0.24

æĿ¥èĩª

0.24

Activations Density 0.007%

statement

No Comments

No Known Activations