INDEX

Explanations

Township

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 alike

-0.29

 slik

-0.28

åĳĢ

-0.27

 plots

-0.26

getVar

-0.26

oure

-0.25

æľīèī²

-0.25

upos

-0.24

 equivalents

-0.24

='#

-0.24

POSITIVE LOGITS

maries

0.26

aml

0.26

á»ĭa

0.26

ÙĬØ§Øª

0.25

(Buffer

0.24

Daw

0.24

å®Ŀè´µçļĦ

0.23

çĶŁæ´»åľ¨

0.23

åľ¨ç¾İåĽ½

0.23

atori

0.23

Activations Density 2.001%

Township

No Comments

No Known Activations