INDEX

Explanations

let

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 commute

-0.29

Ã´le

-0.26

fee

-0.26

 Siri

-0.25

 chart

-0.25

ç»ĻåĬĽ

-0.25

(mi

-0.25

 Liberties

-0.24

hest

-0.24

è¿ĶåĽŀæĲľçĭĲ

-0.24

POSITIVE LOGITS

æİ¢

0.29

Ã±os

0.29

dbc

0.26

ragen

0.26

 Cathedral

0.26

StackSize

0.25

æĻĶ

0.24

åħĥç´ł

0.24

@qq

0.24

ç»ıéªĮ

0.24

Activations Density 1.355%

let

No Comments

No Known Activations