INDEX

Explanations

through

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

 matt

-0.31

 Henderson

-0.27

mob

-0.24

æĸ¯åŁº

-0.24

fact

-0.23

æĸ¹éĿ¢çļĦ

-0.23

 Cassidy

-0.23

 magistrate

-0.23

assignment

-0.23

StringValue

-0.23

POSITIVE LOGITS

[&

0.27

åĪ·

0.26

äº¤

0.26

 parallel

0.26

armor

0.25

[dir

0.25

å¹³å®ī

0.25

pan

0.25

ç»Ń

0.25

_pan

0.25

Activations Density 0.001%

through

No Comments

No Known Activations