INDEX

Explanations

Random text fragments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isse

-0.27

è¶ħ

-0.26

ÙħÙĬØ¹

-0.26

 jednoczeÅĽnie

-0.25

â½´

-0.25

edException

-0.25

 comple

-0.24

UpDown

-0.24

issen

-0.24

kte

-0.24

POSITIVE LOGITS

æ´½

0.33

å¤§çģ«

0.28

Ded

0.27

ä¸Ģåĳ¨

0.26

 (↵↵

0.25

mez

0.25

ä¸ĢåŃĹ

0.25

blah

0.24

 inferred

0.24

æ¼ĶåĶ±

0.24

Activations Density 0.158%

Random text fragments

No Comments

No Known Activations